cad_workflow

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare idempotent and destructive behavior, and the description adds genuinely useful context: document preconditions, argument validation, optional post-change verification, and compensating undo. It does not contradict the annotations and adds behavioral meaning beyond the structured hints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a compact single sentence that front-loads the core action and resource. It lists many relevant behaviors without obvious filler, though the dense chain of clauses makes it slightly less scannable than ideal.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex tool with 8 parameters, nested verification/expectedDocument objects, and no output schema, the description is incomplete. It does not explain what preview returns, how verification failures behave, how expectedDocument matching works, or the operational meaning of rollbackOnFailure and visualMode.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for parameter semantics. It vaguely maps to concepts like expectedDocument, verification, idempotencyKey, and rollbackOnFailure, but it does not explain mode values, visualMode, workflowId, or the steps structure. This is insufficient for 8 parameters with nested objects.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific action ('Preview or apply') and a specific resource ('bounded multi-step CAD change set'), and further distinguishes it from sibling single-purpose CAD tools by mentioning preconditions, verification, idempotency, and undo. This clearly separates cad_workflow from cad_command, cad_edit, cad_undo, and similar siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear usage context: this tool is for bounded multi-step change sets with preview/apply modes and compensating behavior, which implies when it should be chosen over direct editing tools. It does not explicitly state when not to use it or name alternatives, but it is not misleading.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.